Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1619169 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0958. Min Act: -0.0000

Data Index: 353737 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1917816 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1261165 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1022773 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1384255 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.9563. Min Act: -0.0000

Data Index: 644085 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8369. Min Act: -0.0000

Data Index: 738530 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8689. Min Act: -0.0000

Data Index: 892505 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1232467 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1938232 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8510. Min Act: -0.0000

Data Index: 290359 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1346469 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1124231 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1936046 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1892741 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8229. Min Act: -0.0000

Data Index: 680269 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7755. Min Act: -0.0000

Data Index: 265420 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1802833 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 1.2051. Min Range: -1.2051

Max Act: 0.8036. Min Act: -0.0000

Data Index: 929247 (The Pile)

Max Activating Token Index: 932